PhysioNet Overview: Research Resource for Complex Physiologic Signals

The Laboratory for Computational Physiology (LCP) is one of two core laboratories of the National Institutes of Health’s Research Resource for Complex Physiologic Signals, and is the home of the Resource’s PhysioNet web site, the world’s largest repository of freely available recorded physiologic signals, time series, and related open-source software for research. As part of our PhysioNet-related activities, and in cooperation with the annual IEEE-sponsored Computers in Cardiology conference, we also create and host a series of open challenges inviting participants to tackle clinically interesting problems that are unsolved or poorly solved.

A sampling of the group’s interests includes:

(*) Cardiovascular system modeling (RCVSIM), including adaptation to microgravity and orthostatic intolerance
(*) “Intelligent” patient monitoring for intensive care applications (MIMIC, MIMIC 2)
(*) Design and implementation of databases for physiologic signals and related clinical information (PhysioBank)
(*) Novel signal processing techniques for automated or semi-automated patient diagnosis (EDR)
(*) Web-enabled physiologic signal processing, with applications in research and telemedicine (WFDB and WAVE)
(*) Data mining algorithms for efficient searching in very long time series
(*) Assessment of signal quality and detection of events in weakly correlated signals
(*) Multivariate trend analysis and forecasting, with applications in intensive care
(*) Software and systems to support rigorously validated, semi-automated analysis and annotation of recorded physiologic signals for research
(*) Networked instrumentation for acquisition and remote viewing of real-time physiologic data
(*) Automated and semi-automated algorithms for removal of protected health information from clinical data intended for research
(*) Interactive software for improved clinical record-keeping